Abstract: Systems and methods for audio listening devices, comprise a speaker coupled to a first housing, a sound port having a first end and a second end, wherein the first end is coupled to the first housing, and the second end is configured to be inserted in an ear canal of a person such that sound waves emitted from the speaker propagates via a secondary path to the ear canal through the sound port, active noise cancellation (ANC) components configured to generate anti-noise signals through the micro-speakers to cancel external noise, and a first microphone disposed within the sound port at the second end of the sound port such that the first microphone is configured to detect the anti-noise signal that propagates through the sound port via the secondary path and the external noise that propagates via a primary path.

Abstract: Systems and methods for low latency adaptive noise cancellation include an audio sensor to sense environmental noise and generate a noise signal, an audio processing path to receive an audio signal, process the audio signal through an interpolation filter, and generate a primary audio signal having a first sample frequency, an adaptive noise cancellation processor to receive the noise signal and generate an anti-noise signal, a direct interpolator to receive the anti-noise signal and generate an anti-noise signal having the first sample frequency, and a limiter to provide clipping to reduce a number of bits in the anti-noise signal, an adder operable to combine the primary audio signal and the anti-noise signal and generate a combined output signal, and a low latency filter to process the combined output signal.

Abstract: A classification training system for binary and multi-class classification comprises a neural network operable to perform classification of input data, a training dataset including pre-segmented, labeled training samples, and a classification training module operable to train the neural network using the training dataset. The classification training module includes a forward pass processing module, and a backward pass processing module. The backward pass processing module is operable to determine whether a current frame is in a region of target (ROT), determine ROT information such as beginning and length of the ROT and update weights and biases using a cross-entropy cost function and connectionist temporal classification cost function. The backward pass module further computes a soft target value using ROT information and computes a signal output error using the soft target value and network output value.

Abstract: A classification system and method for training a neural network includes receiving a stream of segmented, labeled training data having a sequence of frames, computing a stream of input features data for the sequence of frames, and generating neural network outputs for the sequence of frames in a forward pass through the training data and in accordance weights and biases. The weights and biases are updated in a backward pass through the training data, including determining Region of Target (ROT) information from the segmented, labeled training data, computing modified forward and backward variables based on the neural network outputs and the ROT information, deriving a signal error for each frame within the sequence of frames based on the modified forward and backward variables, and updating the weights and biases based on the derived signal error. An adaptive learning module is provided to improve a convergence rate of the neural network.

Abstract: Classification training systems and methods include a neural network for classification of input data, a training dataset providing segmented labeled training data, and a classification training module operable to train the neural network using the training data. A forward pass processing module is operable to generate neural network outputs for the training data using weights and bias for the neural network, and a backward pass processing module is operable to update the weights and biases in a backward pass, including obtaining Region of Target (ROT) information from the training data, generate a forward-backward masking based on the ROT information, the forward-backward masking placing at least one restriction on a neural network output path, compute modified forward and backward variables based on the neural network outputs and the forward-backward masking, and update the weights and biases.

Abstract: A system and a method provide for protecting a loudspeaker from thermal and/or mechanical failure by monitoring for over-temperature and over-power conditions. The system generates a first gain from a first speaker protection controller in response to a driving voltage and/or a driving current of a loudspeaker, and generates a second gain from a second speaker protection controller in response to the driving voltage and/or a driving current of the loudspeaker, if the temperature exceeds a thermal limit or if the power exceeds a maximum power. The system applies the second gain to an audio signal to lower the audio signal if the first speaker protection controller fails.

Abstract: Adaptive noise cancellation systems and methods comprise a reference sensor operable to sense environmental noise and generate a corresponding reference signal, an error sensor operable to sense noise in a noise cancellation zone and generate a corresponding error signal, a noise cancellation filter operable to receive the reference signal and generate an anti-noise signal to cancel the environmental noise in the cancellation zone, an adaptation module operable to receive the reference signal and the error signal and adaptively adjust the anti-noise signal, and a transient activity detection module operable to receive the reference signal, detect a transient noise event and selectively disable the adaptation module during the detected transient noise event.

Abstract: Adaptive noise cancellation systems and methods comprise a reference sensor operable to sense environmental noise and generate a corresponding reference signal, an error sensor operable to sense noise in a noise cancellation zone and generate a corresponding error signal, a noise cancellation filter operable to receive the reference signal and generate an anti-noise signal to cancel the environmental noise in the cancellation zone, an adaptation module operable to receive the reference signal and the error signal and adaptively adjust the anti-noise signal. The adaptation module includes a noise amplification control module operable to adaptively control noise amplification in at least one hiss region of the anti-noise signal, while achieving cancellation in non-hiss regions of the anti-noise signal.

Abstract: Adaptive noise cancellation systems and methods include a reference sensor to sense environmental noise and generate a corresponding reference signal, an error sensor to sense noise in a noise cancellation zone and generate a corresponding error signal, a noise cancellation path including a noise cancellation filter and a variable gain component, the noise cancellation path receiving the reference signal and generating an anti-noise signal to cancel noise at an eardrum reference point, and an adaptation module to receive the reference signal and the error signal and adaptively adjust weights of the noise cancellation filter and/or the variable gain component. An adaptive gain control block updates the variable gain component. Inputs to the adaptive gain control block are conditioned using programmable filters to protect against low frequency transients and/or high frequency distractors in the environmental noise. The programmable filters are tuned to optimize cancellation at an eardrum reference point.

Abstract: An acoustic event detection and classification system includes a start-end point detector and multi-class acoustic event classification. A classification training system comprises a neural network configured to perform classification of input data, a training dataset including pre-segmented, labeled training samples, and a classification training module configured to train the neural network using the training dataset. The classification training module includes a forward pass processing module, and a backward pass processing module. The backward pass processing module is configured to determine whether a current frame is in a region of target (ROT), determine ROT information such as beginning and length of the ROT and update weights and biases using a cross-entropy cost function and a many-or-one detection (MOOD) cost function. The backward pass module further computes a soft target value using ROT information and computes a signal output error using the soft target value and network output value.

Abstract: An end detector configured to receive the feature data and detect an end point of a keyword, and a start detector configured to receive an indication of the detected end point and process the feature data associated with corresponding input frames to detect a start point of the keyword. The start detector and end detector comprise neural networks trained through a process using a cross-entropy cost function for non-Region of Target (ROT) frames and a One-Spike Connectionist Temporal Classification cost function for ROT frames.

Abstract: A classification training system for binary and multi-class classification comprises a neural network operable to perform classification of input data, a training dataset including pre-segmented, labeled training samples, and a classification training module operable to train the neural network using the training dataset. The classification training module includes a forward pass processing module, and a backward pass processing module. The backward pass processing module is operable to determine whether a current frame is in a region of target (ROT), determine ROT information such as beginning and length of the ROT and update weights and biases using a cross-entropy cost function and One Spike Connectionist Temporal Classification (OSCTC) cost function. The backward pass module further computes a soft target value using ROT information and computes a signal output error using the soft target value and network output value.

Abstract: Systems and methods for enhancing a headset user's own voice include an outside microphone, an inside microphone, audio input components operable to receive a plurality of time-domain microphone signals, including an outside microphone signal from the outside microphone and an inside microphone signal from the inside microphone, a subband decomposition module operable to transform the time-domain microphone signals to frequency domain subband signals, a voice activity detector operable to detect speech presence and absence in the subband signals, a speech extraction module operable to predict a clean speech signal in each of the inside microphone signal and the outside microphone signal, and cancel audio sources other than a headset user's own voice by combining the predicted clean speech signal from the inside microphone signal and the predicted clean speech signal from the outside microphone signal, and a postfiltering module operable to reduce residual noise.

Abstract: Systems and methods for processing multichannel audio signals include receiving a multichannel time-domain audio input, transforming the input signal to plurality of multi-channel frequency domain, k-spaced under-sampled subband signals, buffering and delaying each channel, saving a subset of spectral frames for prediction filter estimation at each of the spectral frames, estimating a variance of the frequency domain signal at each of the spectral frames, adaptively estimating the prediction filter in an online manner using a recursive least squares (RLS) algorithm, linearly filtering each channel using the estimated prediction filter, nonlinearly filtering the linearly filtered output signal to reduce residual reverberation and the estimated variances, producing a nonlinearly filtered output signal, and synthesizing the nonlinearly filtered output signal to reconstruct a dereverberated time-domain multi-channel audio signal.

Abstract: Various techniques are provided to perform enhanced automatic speech recognition. For example, a subband analysis may be performed that transforms time-domain signals of multiple audio channels in subband signals. An adaptive configurable transformation may also be performed to produce single or multichannel-based features whose values are correlated to an Ideal Binary Mask (IBM). An unsupervised Gaussian Mixture Model (GMM) model fitting the distribution of the features and producing posterior probabilities may also be performed, and the posteriors may be combined to produce deep neural network (DNN) feature vectors. A DNN may be provided that predicts oracle spectral gains from the input feature vectors. Spectral processing may be performed to produce an estimate of the target source time-frequency magnitudes from the mixtures and the output of the DNN. Subband synthesis may be performed to transform signals back to time-domain.

Abstract: Systems and methods for low latency adaptive noise cancellation include an audio sensor to sense environmental noise and generate a noise signal, an audio processing path to receive an audio signal, process the audio signal through an interpolation filter, and generate a primary audio signal having a first sample frequency, an adaptive noise cancellation processor to receive the noise signal and generate an anti-noise signal, a direct interpolator to receive the anti-noise signal and generate an anti-noise signal having the first sample frequency, and a limiter to provide clipping to reduce a number of bits in the anti-noise signal, an adder operable to combine the primary audio signal and the anti-noise signal and generate a combined output signal, and a low latency filter to process the combined output signal.

Abstract: A selective audio source enhancement system includes a processor and a memory, and a pre-processing unit configured to receive audio data including a target audio signal, and to perform sub-band domain decomposition of the audio data to generate buffered outputs. In addition, the system includes a target source detection unit configured to receive the buffered outputs, and to generate a target presence probability corresponding to the target audio signal, as well as a spatial filter estimation unit configured to receive the target presence probability, and to transform frames buffered in each sub-band into a higher resolution frequency-domain. The system also includes a spectral filtering unit configured to retrieve a multichannel image of the target audio signal and noise signals associated with the target audio signal, and an audio synthesis unit configured to extract an enhanced mono signal corresponding to the target audio signal from the multichannel image.

Abstract: Systems and methods for processing an audio signal include an audio input operable to receive an input signal comprising a time-domain, single-channel audio signal, a subband analysis block operable to transform the input signal to a frequency domain input signal comprising a plurality of k-spaced under-sampled subband signals, a reverberation reduction block operable to reduce reverberation effect, including late reverberation, in the plurality of k-spaced under-sampled subband signals, a noise reduction block operable to reduce background noise from the plurality of k-spaced under-sampled subband signals, and a subband synthesis block operable to transform the subband signals to the time-domain, thereby producing an enhanced output signal.

Abstract: An audio driver equipped with a distortion compensation unit corrects for detected distortion and includes a digital to analog converter (DAC), an amplifier, and an output driver that drives a loudspeaker. Between the output driver and the loudspeaker, the audio driver can include a series resistor and a differential amplifier to measure the voltage across the resistor. A distortion detection unit can use the detected voltage to determine whether distortion, such as rub and buzz distortion is present. The distortion detection unit can comprise an analog to digital converter (ADC) to digitize the voltage data, an FFT to transform the voltage data into frequency information, a root-mean-square (RMS) module that measures the energy at each frequency, and an analysis module which looks for the distortion signature in the energy spectrum.

Abstract: A system and a method provide for protecting a loudspeaker from thermal and/or mechanical failure by monitoring for over-temperature and over-power conditions. The system generates a first gain from a first speaker protection controller in response to a driving voltage and/or a driving current of a loudspeaker, and generates a second gain from a second speaker protection controller in response to the driving voltage and/or a driving current of the loudspeaker, if the temperature exceeds a thermal limit or if the power exceeds a maximum power. The system applies the second gain to an audio signal to lower the audio signal if the first speaker protection controller fails.